Codestral 2508 vs DeepSeek V3.1 Terminus
Updated October 21, 2026. 7 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Neither model has a coding score yet, so the two cannot be ranked on coding.
Codestral 2508 has the edge where output tokens cost 1.1x less, and where the context window is larger, 256K against 164K tokens.
- Shared results
- 7
- Codestral 2508 only
- 0
- DeepSeek V3.1 Terminus only
- 37
- Like-for-like categories
- 2 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
No call
Only DeepSeek V3.1 Terminus has a AA Intelligence Index result, 14.8.
Directional only
Agentic work
AA Agentic Index
No call
Only DeepSeek V3.1 Terminus has a AA Agentic Index result, 6.8.
Directional only
Web design
Design Arena: websites
DeepSeek V3.1 Terminus
DeepSeek V3.1 Terminus leads, 1187 against 1013.
Same board, both measured
Long documents
Listed context window
Codestral 2508
Codestral 2508 takes 256K tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Codestral 2508
Codestral 2508 $0.0008, DeepSeek V3.1 Terminus $0.0008 per turn.
List prices
At a glance
- Coding index
- Codestral 2508 not benchmarked, DeepSeek V3.1 Terminus not benchmarked.
- Widest category
- Coding, 20.2 points apart on average over 1 shared benchmark.
- Widest single gap
- Design Arena: websites: Codestral 2508 1013 against DeepSeek V3.1 Terminus 1187, 21.8 points apart on a 0 to 100 scale.
- Output price
- Codestral 2508 $0.90 against DeepSeek V3.1 Terminus $1.0142 per million output tokens, 1.1x apart.
- Context window
- Codestral 2508 takes 256K tokens, DeepSeek V3.1 Terminus 164K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Codestral 2508 | Bars | DeepSeek V3.1 Terminus | Ties |
|---|---|---|---|---|
| Coding | 0 | 1 | ||
| Web design | 0 | 6 | ||
| All shared boards | 0 | 7 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index01
| Benchmark | Codestral 2508 | DeepSeek V3.1 Terminus | Leader |
|---|---|---|---|
| AA Coding Index | Not measured | 43.5 | Only DeepSeek V3.1 Terminus measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 79.8% | Only DeepSeek V3.1 Terminus measured |
| SciCode | Not measured | 38.0% | Only DeepSeek V3.1 Terminus measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 31.8% | Only DeepSeek V3.1 Terminus measured |
| ALE-Bench | 137.8 | 745.2 | DeepSeek V3.1 Terminus |
| LMArena Text: coding | Not measured | 1425 | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: software and IT | Not measured | 1426 | Only DeepSeek V3.1 Terminus measured |
| Neither model has a result on the other 31 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Codestral 2508 | DeepSeek V3.1 Terminus | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 14.8 | Only DeepSeek V3.1 Terminus measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Codestral 2508 | DeepSeek V3.1 Terminus | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 6.8 | Only DeepSeek V3.1 Terminus measured |
| τ²-Bench Telecom | Not measured | 37.1% | Only DeepSeek V3.1 Terminus measured |
| Neither model has a result on the other 37 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | Codestral 2508 | DeepSeek V3.1 Terminus | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | Not measured | 79.2% | Only DeepSeek V3.1 Terminus measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 16.4% | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: hard prompts | Not measured | 1426 | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: hard prompts in English | Not measured | 1432 | Only DeepSeek V3.1 Terminus measured |
| Neither model has a result on the other 17 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Codestral 2508 | DeepSeek V3.1 Terminus | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 89.7 | Only DeepSeek V3.1 Terminus measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 89.7% | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: math | Not measured | 1402 | Only DeepSeek V3.1 Terminus measured |
| Neither model has a result on the other 10 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Codestral 2508 | DeepSeek V3.1 Terminus | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | Not measured | 85.1% | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: science | Not measured | 1451 | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: medicine and healthcare | Not measured | 1468 | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: legal and government | Not measured | 1457 | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: business and finance | Not measured | 1414 | Only DeepSeek V3.1 Terminus measured |
| Neither model has a result on the other 12 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | Codestral 2508 | DeepSeek V3.1 Terminus | Leader |
|---|---|---|---|
| Design Arena: websites | 1013 | 1187 | DeepSeek V3.1 Terminus |
| Design Arena: UI components | 1017 | 1182 | DeepSeek V3.1 Terminus |
| Design Arena: game dev | 968 | 1131 | DeepSeek V3.1 Terminus |
| Design Arena: data viz | 1017 | 1167 | DeepSeek V3.1 Terminus |
| Design Arena: 3D | 1020 | 1141 | DeepSeek V3.1 Terminus |
| Design Arena: all code categories | 1007 | 1175 | DeepSeek V3.1 Terminus |
| Design Arena: SVG | Not measured | 1065 | Only DeepSeek V3.1 Terminus measured |
| Neither model has a result on the other 2 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index15 boards, none shared
| Benchmark | Codestral 2508 | DeepSeek V3.1 Terminus | Leader |
|---|---|---|---|
| IFBench | Not measured | 57.0% | Only DeepSeek V3.1 Terminus measured |
| Long context reasoning (AA-LCR) | Not measured | 69.3% | Only DeepSeek V3.1 Terminus measured |
| DTBench | Not measured | 81.3% | Only DeepSeek V3.1 Terminus measured |
| LMCA | Not measured | 28.6% | Only DeepSeek V3.1 Terminus measured |
| LMArena Text | Not measured | 1419 | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: instruction following | Not measured | 1404 | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: creative writing | Not measured | 1403 | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: English | Not measured | 1429 | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: non-English | Not measured | 1408 | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: Russian | Not measured | 1435 | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: Polish | Not measured | 1427 | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: multi-turn | Not measured | 1411 | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: longer queries | Not measured | 1422 | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: writing and language | Not measured | 1409 | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: entertainment and media | Not measured | 1391 | Only DeepSeek V3.1 Terminus measured |
| Neither model has a result on the other 31 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Codestral 2508 | DeepSeek V3.1 Terminus | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Codestral 2508 costs less
Repository review
50K input + 3K output tokens
Codestral 2508 costs less
Agent loop
200K input + 10K output tokens
Codestral 2508 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Mistral Codestral 2508 | DeepSeek V3.1 Terminus |
|---|---|---|
| Maker | Mistral AI | DeepSeek |
| Weights | No public weights listed | Open weights |
| Released | August 1, 2025 | September 22, 2025 |
| Context window | 256K | 164K |
| Input $/Mtok | $0.30 | $0.3063 |
| Output $/Mtok | $0.90 | $1.0142 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Codestral 2508 better than DeepSeek V3.1 Terminus for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Codestral 2508 has the edge where output tokens cost 1.1x less, and where the context window is larger, 256K against 164K tokens.
Which is cheaper, Codestral 2508 or DeepSeek V3.1 Terminus?
Codestral 2508 costs $0.30 per million input tokens and $0.90 per million output tokens; DeepSeek V3.1 Terminus costs $0.3063 and $1.0142. Cost per solved task is known for neither of them.
Which has the bigger context window, Codestral 2508 or DeepSeek V3.1 Terminus?
Codestral 2508, with 256K tokens against 164K.
How many benchmarks is the Codestral 2508 vs DeepSeek V3.1 Terminus comparison based on?
7 benchmarks have a result for both models as of October 21, 2026. Codestral 2508's coding index rests on 0 independent benchmarks and DeepSeek V3.1 Terminus's on 0. Where only one model has a result, the page says so instead of naming a winner.